Characteristic parameters of shield supporting in fully mechanized mining, especially time-weighted average pressure (TWAP), are crucial for the analysis and prediction of roof weightings in longwall panels. Despite the leap-forward development of underground data collection and transmission, mining and regional correlation analysis of massive shield data remains challenging. In this study, a hybrid machine learning model integrating the long short-term memory (LSTM) networks and the Bayesian optimization (BO) algorithm was developed to predict TWAP based on the setting pressure (SP), revised setting pressure (RSP), final pressure (FP), number of yielding (NY), TWAP in the last supporting cycle (TWAP (last)), and loading rate in each period. Statistical measures including the mean square error and mean absolute error were used to validate and compare the prediction performances of the BP model, the LSTM model, and the BO-LSTM model. Furthermore, sensitivity studies were carried out to evaluate the importance of input parameters. The results show that the BO-LSTM model is robust in predicting TWAP. FP and TWAP (last) are the most important input parameters in TWAP prediction, followed by RSP and NY. Moreover, the total importance scores of loading rates reach 0.229, indicating the necessity of including these parameters into the dataset. The proposed BO-LSTM model is capable of predicting TWAP which serves for shield-roof status intelligent perception.
Fracturing and heat injection are promising methods for in situ modification of low-permeability reservoirs to enhance coalbed methane (CBM) recovery. The technical processes enable substantial water residence in the reservoirs and cause rebalance and redistribution of the stress and temperature fields around the wells or boreholes. In this study, a dual-porosity permeability model is established. The coupling effects of variable stresses and temperatures (below 100 °C) on the permeability evolution of gas-saturated wet coal are also studied. The results show that (1) the mean effective stress and temperature enabled complicated nonlinear decreasing trends in permeability, and sensitivity analysis of input parameters by the random forest method indicates that the effect of stress on permeability was much greater than that of temperature; (2) the relationship between incremental effective stress and permeability can be well expressed by a new function, while initial permeability and variations in thermal cracking and stiffness of the matrix during heating will affect fit coefficients of the function; and (3) as signified by substantial breakthrough in thermal cracks and fractures, permeability evolution during heating consists of phase I and phase II, and the evolution performance in phase I was more complicated as it is controlled by external stress conditions and also related to mutual competition between positive effects (due to thermal volatilization and sorption-induced matrix shrinkage) and negative effects (due to thermal expansion and thermal cracking). Moreover, variability of permeability versus temperature at low deviatoric stress (0 MPa) differed from that at high deviatoric stresses (3–12 MPa). These results would be beneficial for permeability prediction and CBM extraction design.
Extensive soft-rock floor heave in gob-side entry retaining considerably restricts the efficient and sustainable production of the mine. The mechanical capacities of roadway roof and floor strata are discussed through laboratory tests by taking the N2301 fully caving surface auxiliary transport gate road of the Ancient City Coal Mine in the Lu’an Mining Area of Shanxi Province as an engineering background. The stress distribution law of gob-side entry in mining the working surface was explored based on numerical simulation. After that, the mechanical mechanism of floor heave was studied through theoretical analysis. High lead abutment pressure and horizontal stress were superimposed in front of the working surface to cause soft-rock floor heave. The bulk weight of the high overburden was unevenly transmitted to the two sides because of the roof cantilever structure of entry retaining in the rear of the working face. The roadway floor produced an asymmetric sliding force, which caused the occurrence of floor heave. The control technology of floor heave combining the pressure relief of floor blasting and roof cutting was proposed taking account of the mechanism of floor heave. Then, the stress environment of the surrounding rock was improved by the deep hole blasting of the floor. Gob-side roof cutting was used to reduce impact of the bulk weight of the overburden on the surrounding rock deformation of the roadway. A test was conducted after verifying the control effect of blasting pressure relief on roadway floor heave through a similar simulation. Field tests indicated that the maximum floor heave was 168 mm at 250 m in the rear of the working surface, and floor heave was controlled. This study offers a more scientifically sound theoretical reference for controlling floor heave in gob-side entry retaining, which can significantly advance the sustainable development of gob-side entry retaining technology in coal mining.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.